jobctl

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Job application tracker for developers - AI agents write over MCP, you review in a dashboard.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "jobctl": {
      "url": "https://app.jobctl.app/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (11)

• add_application

  Track a new job application. Pass either a single `raw` line — `add_application({raw: "Bosch, Tech Lead, prio A, due friday, remote, via LinkedIn"})` — or structured fields (`company` and `role` required then). Returns the created application and possible-duplicate warnings; if duplicates are listed, tell the user instead of creating again.

  Parameters:

  • raw — string — Free-form line: "Company, Role, prio A|B|C, due <date>, remote|hybrid|onsite, via <source>, https://…, in <location>, applied <date>"
  • url — string — Link to the job posting
  • role — string
  • remote — string
  • source — string — LinkedIn, referral, recruiter, Easy Apply…
  • status — string
  • company — string
  • location — string
  • priority — string — A = top priority
  • applied_at — string — ISO date YYYY-MM-DD
  • cv_variant — string — Which CV was sent: DE, EN, AI-focused…
  • match_notes — string — Markdown match assessment: why the candidate fits this role — strengths vs requirements, gaps, level/salary advice, process notes. Save your vacancy analysis here so it is not lost; shown as an expandable section in the dashboard.
  • next_action — string — e.g. "follow-up", "thank-you email"
  • remote_note — string — e.g. "2 days office"
  • salary_asked — integer — What the candidate asked for — yearly gross EUR as a plain number, e.g. 110000
  • salary_range — integer — Posting salary range upper bound — yearly gross EUR, plain number
  • next_action_due — string — ISO date YYYY-MM-DD
  • salary_range_min — integer — Posting salary range lower bound — yearly gross EUR, plain number
  • next_interview_at — string — ISO datetime, e.g. 2026-07-20T14:00:00+02:00

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• list_applications read-only

  List job applications. Filter by view (active = default working set, archive = rejected/withdrawn/no-response), status list, priority, or free-text search in company/role. Example: `list_applications({view: "active"})`, `list_applications({q: "bosch"})`.

  Parameters:

  • q — string — Search in company/role
  • view — string
  • limit — integer
  • status — string — Comma-separated: started_apply, waiting_referral, applied, waiting, interview, offer, accepted, rejected, no_response, on_hold, withdrawn, archived
  • priority — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• update_application

  Update fields of an application (get the id from list_applications). Status changes are logged to the timeline automatically. Example: `update_application({id: "…", status: "interview", next_action: "prepare system design", next_action_due: "2026-07-20"})`.

  Parameters:

  • id (required) — string
  • url — string — Link to the job posting
  • role — string
  • remote — string
  • source — string — LinkedIn, referral, recruiter, Easy Apply…
  • status — string
  • company — string
  • location — string
  • priority — string — A = top priority
  • applied_at — string — ISO date YYYY-MM-DD
  • cv_variant — string — Which CV was sent: DE, EN, AI-focused…
  • match_notes — string — Markdown match assessment: why the candidate fits this role — strengths vs requirements, gaps, level/salary advice, process notes. Save your vacancy analysis here so it is not lost; shown as an expandable section in the dashboard.
  • next_action — string — e.g. "follow-up", "thank-you email"
  • remote_note — string — e.g. "2 days office"
  • salary_asked — integer — What the candidate asked for — yearly gross EUR as a plain number, e.g. 110000
  • salary_range — integer — Posting salary range upper bound — yearly gross EUR, plain number
  • next_action_due — string — ISO date YYYY-MM-DD
  • salary_range_min — integer — Posting salary range lower bound — yearly gross EUR, plain number
  • next_interview_at — string — ISO datetime, e.g. 2026-07-20T14:00:00+02:00

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• add_note

  Append a free-text note to an application timeline — recruiter call summaries, interview instructions, pasted messages. Multiline markdown is fine. Example: `add_note({application_id: "…", text: "Recruiter: team of 5, on-call rotation, offer range 85-95k"})`.

  Parameters:

  • application_id (required) — string
  • text (required) — string

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• log_interview

  Log an interview for an application (max 10 per application): when it takes place, its status (planned or done), who attends (each with an optional profile link), related links (prep materials the company sent, meeting URL), and a short recap of what was discussed. Also keeps the application's next-interview date in sync. Example: `log_interview({application_id: "…", scheduled_at: "2026-07-20T14:00:00+02:00", status: "planned", attendees: [{name: "Anna Weber (HR)", url: "https://linkedin.com/in/annaweber"}], links: [{label: "Prep materials", url: "https://company.com/interview-prep"}], recap: "System design round"})`.

  Parameters:

  • application_id (required) — string
  • scheduled_at (required) — string — ISO datetime with offset, e.g. 2026-07-20T14:00:00+02:00
  • links — array — Related links: prep materials, meeting URL, docs
  • recap — string — Short recap of what was discussed
  • status — string — planned (default) or done
  • attendees — array — Who attends, each with an optional profile link

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• get_due read-only

  What is burning today: applications with next_action_due today or overdue. Call this when the user asks "what should I do today?" about their job search.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• get_planned read-only

  What is actually SCHEDULED: interviews with their time, attendees and meeting links, plus the actions falling due, for today, tomorrow, or the next seven days. Use this whenever the user asks what is planned, what the day or week looks like, or before proposing a time to anyone — get_due only knows action deadlines and is blind to booked interviews. Example: `get_planned({range: "tomorrow"})`.

  Parameters:

  • range — string — today (default), tomorrow, or week (today plus the next 6 days)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

• attach_analysis destructive

  Attach a markdown company analysis (research you produced) to an application. Single document per application — a new call REPLACES the previous one. Max 100000 bytes (~100 KB) of utf-8. The user reads it in the dashboard, e.g. before an interview. Example: `attach_analysis({application_id: "…", markdown: "# Bosch\n\n## Culture…"})`.

  Parameters:

  • application_id (required) — string
  • markdown (required) — string — The analysis as markdown

  Hints: read-only no · destructive yes · idempotent not declared · open-world not declared

• attach_file destructive

  Attach or replace a file on an application so the user sees it in the dashboard: a CV/resume (kind: 'cv') or a cover letter (kind: 'cover_letter'). Pass the file bytes as base64 in data_base64. One file per (application, kind) - a new call REPLACES the previous one. Max ~5 MB; pdf/doc/docx/txt/md (MIME is inferred from the filename if you omit it). Call this whenever you generate a tailored CV or cover letter for an application. Example: `attach_file({application_id: "…", kind: "cv", filename: "CV_Cursor.pdf", data_base64: "JVBERi0…"})`.

  Parameters:

  • application_id (required) — string
  • kind (required) — string
  • filename (required) — string
  • data_base64 (required) — string — Base64-encoded file bytes
  • mime — string — Optional; inferred from the filename extension when omitted

  Hints: read-only no · destructive yes · idempotent not declared · open-world not declared

• attach_interview_file

  Attach prep material to a specific interview so the user sees it next to that round in the dashboard: the prep document you wrote, the job description, a deck, notes the company sent. Max 3 files per interview, 20000000 bytes (20 MB) each; pass the bytes as base64. Get interview ids from get_application. Example: `attach_interview_file({application_id: "…", interview_id: "…", filename: "prep-round2.md", data_base64: "IyBQcmVw…"})`.

  Parameters:

  • application_id (required) — string
  • interview_id (required) — string
  • filename (required) — string
  • data_base64 (required) — string — Base64-encoded file bytes
  • mime — string — Optional; inferred from the filename extension when omitted

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• get_application read-only

  Full detail of one application: all fields, contacts, recent timeline events, and whether a company analysis is attached (fetch it via the dashboard or attach_analysis to replace).

  Parameters:

  • id (required) — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world not declared

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.